Onit

AI-driven enterprise legal management platform

AI Engineer

AI Application EngineeringConfirmed live in the last 24 hours

Full-timePune, Maharashtra, IndiaNo salary listedHybrid

About the Job

Requirements

Strong software engineering background, preferably in Python, and experience shipping backend services.
Hands-on experience building agentic large language model systems from first principles, including agent loops, tool interfaces, planning and replanning, memory and state, and failure handling.
Strong context engineering ability, including retrieval strategies, routing, grounding, context budgeting, and long-context tradeoffs.
Strong evaluation discipline, including golden datasets, regression gating, automated evaluation pipelines, and online monitoring.
Practical experience with large language model APIs such as OpenAI, Azure OpenAI, Anthropic, or Gemini, and AI orchestration frameworks.
Experience shipping a large language model or agent system in production and explaining its failure modes, regression evaluations, cost and latency improvements, monitoring, and safe iteration.
Experience with cloud platforms such as AWS or Google Cloud Platform, microservices, and event-driven systems is preferred.
Experience with observability stacks such as OpenTelemetry, Datadog, or Honeycomb, and AI-specific tools such as Langfuse, Braintrust, HumanLoop, or MLflow is preferred.
Experience with workflow orchestration for long-running jobs using Temporal, Celery, or Airflow is preferred.
Experience building enterprise AI features involving permissions, auditability, or compliance constraints is preferred.
Experience with safety and policy layers, including personally identifiable information handling, prompt injection defenses, or sandboxed tool execution, is preferred.

Responsibilities

Build and integrate AI-driven features using large language model APIs, including OpenAI, Azure OpenAI, Anthropic, and Gemini on Vertex AI.
Design and implement tool-using agents with structured function calling, schema validation, retries, and fallbacks.
Build multi-agent workflows when appropriate, such as planner/worker, reviewer/critic, and specialist routing, and choose simpler architectures when they are more suitable.
Create agentic workflows for document understanding, extraction, reasoning over evidence, task automation, and multi-step decision support.
Own context engineering end-to-end, including dynamic context assembly from retrieval, state, and tool outputs; context budgeting and compression or summarization; and grounding strategies to reduce hallucinations and improve consistency.
Implement retrieval-augmented generation and search workflows using vector stores and embedding services.
Establish evaluation frameworks for accuracy, reliability, and output quality.
Build task-specific evaluation suites with golden datasets, adversarial cases, regression tests, and rubric-based scoring.
Set up automated evaluation pipelines and release gates compatible with continuous integration and delivery, tied to prompt, model, and version changes.
Define and monitor online metrics such as task success rate, human override rate, safety flags, latency, and cost, and run experiments or A/B tests where appropriate.
Use large language model-as-judge methods responsibly by calibrating and validating them and pairing them with human labels when needed.
Develop scalable backend services and APIs incorporating AI functionality.
Integrate AI pipelines into existing cloud, microservices, and event-driven architectures.
Implement observability and analytics for AI features, including tracing, evaluations, prompt versioning, and cost tracking, using tools such as Langfuse or OpenTelemetry-compatible stacks.
Ensure the reliability, uptime, performance, and security of AI services.
Build internal tooling for evaluation, testing, prompt and version management, and safe deployment.
Partner with product managers, designers, the Chief Architect, and domain subject-matter experts to shape AI-first solutions.
Rapidly prototype concepts and iterate based on user feedback and measurable evaluation results.
Translate business problems into well-structured AI workflows without requiring machine-learning model training.
Document system behavior, known failure modes, and operational playbooks.
Implement guardrails, checks, and fallback logic for safe and predictable AI behavior.
Help define and follow compliance, privacy, and responsible AI guidelines.
Design for safe tool execution using bounded actions, permissions, escalation paths, and human-in-the-loop review.
Ship a production agent workflow end-to-end, including tracing and observability, an offline evaluation suite with regression gates, cost and latency targets and monitoring, and documented failure modes and fallback paths within the first 90 days.

About Onit

We're redefining the future of legal operations through the power of AI. Our cutting-edge platform streamlines enterprise legal management, matter management, spend management and contract lifecycle processes, transforming manual workflows into intelligent, automated solutions.

We’re a team of innovators using AI at the core to help legal departments become faster, smarter, and more strategic. As we continue to grow and expand the capabilities of our new AI-centric platform, we’re looking for bold thinkers and builders who are excited to shape the next chapter of legal tech.

If you're energized by meaningful work, love solving complex problems, and want to help modernize how legal teams operate, we’d love to meet you.

Agentic AI Feature & Workflow Development

Build and integrate AI-driven features using LLM APIs (OpenAI / Azure OpenAI, Anthropic, Gemini on Vertex AI)

Design and implement tool-using agents (structured function calling, schema validation, retries, fallbacks)

Build multi-agent workflows when appropriate (e.g., planner/worker, reviewer/critic, specialist routing) and know when a simpler architecture is better

Create agentic workflows such as document understanding, extraction, reasoning over evidence, task automation, and multi-step decision support

Own context engineering end-to-end:

dynamic context assembly (retrieval + state + tool outputs)

context budgeting and compression/summarization

grounding strategies to reduce hallucinations and improve consistency

Implement retrieval-augmented generation (RAG) and search workflows using off-the-shelf vector stores and embedding services

Evaluation, Quality & Iteration (Core)

Establish evaluation frameworks for accuracy, reliability, and output quality

Build task-specific eval suites: golden datasets, adversarial cases, regression tests, and rubric-based scoring

Set up automated evaluation pipelines and release gates (CI/CD-friendly) tied to prompt/model/version changes

Define and monitor online metrics (e.g., task success rate, human override rate, safety flags, latency, cost) and run experiments/A-B tests where appropriate

Use LLM-as-judge responsibly: calibrate, validate, and pair with human labels when needed

Engineering, Integration & Observability

Develop scalable backend services and APIs that incorporate AI functionality

Integrate AI pipelines into existing cloud, microservices, and event-driven architectures

Implement observability and analytics for all AI features (tracing, evaluations, prompt versioning, cost tracking) Example tooling: Langfuse (and/or OpenTelemetry-compatible stacks)

Ensure reliability, uptime, performance, and security of AI services

Build internal tooling for evaluation, testing, prompt/version management, and safe deployment

Product & Collaboration

Partner with product managers, designers, the Chief Architect, and domain SMEs to shape AI-first solutions

Rapidly prototype concepts and iterate based on user feedback and measurable eval results

Translate business problems into well-structured AI workflows without requiring ML model training

Document system behavior, known failure modes, and operational playbooks

Governance & Safety

Implement guardrails, checks, and fallback logic for safe and predictable AI behavior

Help define and follow compliance, privacy, and responsible AI guidelines

Design for safe tool execution (bounded actions, permissions, escalation paths, human-in the-loop review

Core Strengths (Required)

Strong software engineering background (Python preferred) and experience shipping backend services

Deep hands-on experience building agentic LLM systems from first principles: agent loops, tool interfaces, planning/replanning, memory/state, and failure handling

Strong context engineering ability: retrieval strategies, routing, grounding, context budgeting, and long-context tradeoffs

Strong evaluation discipline: golden datasets, regression gating, automated eval pipelines, and online monitoring

Practical experience with LLM APIs (OpenAI/Azure OpenAI/Anthropic/Gemini) and AI orchestration frameworks

Excellent debugging, systems thinking, and problem decomposition skills

Comfortable operating in fast-paced, ambiguous environments with high ownership

Signals We Value

You’ve shipped an LLM/agent system in production and can clearly explain:

the failure modes you discovered

the evals you built to catch regressions

how you improved cost/latency while increasing quality

how you monitored and iterated safely over time

You keep up with industry developments (model releases, frameworks, best practices) and can translate them into pragmatic improvement

Nice to Have

Experience with cloud platforms (AWS and/or GCP), microservices, and event-driven systems

Experience with observability stacks (OpenTelemetry, Datadog, Honeycomb) and AI-specific tooling (e.g., Langfuse, Braintrust, HumanLoop, MLFlow)

Experience with workflow orchestration for long-running jobs (Temporal, Celery, Airflow)

Experience building enterprise AI features (permissions, auditability, compliance constraints)

Experience with safety/policy layers (PII handling, prompt injection defenses, sandboxed tool execution)

Why Join Us

Build core AI capabilities that directly impact users and product strategy

Work on cutting-edge, real-world agentic systems—focused on applied engineering (no model training required)

High ownership, fast iteration cycles, and strong cross-functional collaboration

Competitive compensation and opportunities for rapid advancement

What Your First 90 Days Could Look Like

Ship one production agent workflow end-to-end with:

tracing + observability

an offline eval suite with regression gates

cost/latency targets and monitoring

documented failure modes and fallback path

Benefits & Perks That Support You:

Onit offers a comprehensive total rewards package designed to support the whole employee at work and beyond:

Health Coverage: Employee and immediate family members.

Time Away: Flexible paid time off and 10 company paid holidays annually.

Family Support: Exceptional paid leave for birth parents, non-birth parents, and caregivers. Onit also offers surrogacy and adoption reimbursement.

Income Protection: 100% employer-paid life and disability insurance.

Additional Coverage Options: Voluntary benefits including hospital indemnity, critical illness, accident.

Tax-Advantaged Accounts: Flexi, NPS.

Community Engagement: One paid volunteer day each year to give back to the community.

Our Commitment to Applicants

We know that not everyone will check every box in a job description. At Onit, we value diversity, inclusion, and authenticity. If you’re excited about this role but your experience doesn’t align perfectly with every qualification, we encourage you to apply. You may be exactly who we’re looking for.

Onit Values

Customer First - Customer success is our success. We deliver value, listen, and act on customer needs.

Purposeful Innovation - Innovation fuels our growth. We harness creativity to solve problems and lead with the intentions and expertise.

Win as One - Teamwork is how we win. We are accountable, act with integrity, and communicate openly.

Intentional Growth - Our people are the difference. We create an environment with compelling work, impactful contributions, and career growth.

Onit

AI Engineer

About the Job

Requirements

Responsibilities

Agentic AI Feature & Workflow Development

Evaluation, Quality & Iteration (Core)

Engineering, Integration & Observability

Product & Collaboration

Governance & Safety

Core Strengths (Required)

Signals We Value

Nice to Have

Why Join Us

What Your First 90 Days Could Look Like

About the Company

Onit

Recently Posted Jobs