S

Safe Security

AI-powered cybersecurity risk analytics platform

Software Engineer 3 – Engineering Productivity - AI

AI Application EngineeringConfirmed live in the last 24 hours
Full-timeBengaluru, Karnataka, IndiaIn-person

About the Job

Requirements

  • At least 6 years of experience building production software, with SDE3-level ownership of production systems.
  • Strong proficiency in Python, Java, Go, or an equivalent programming language, with experience shipping production services and reviewing others' code.
  • Solid grounding in distributed systems, APIs and microservices, and software architecture.
  • Hands-on experience with cloud infrastructure and continuous integration and continuous delivery (CI/CD).
  • Demonstrated experience building developer tooling and automation that other engineers used.
  • Practical experience with large language models (LLMs) and agentic systems in real systems, not only experiments.
  • Ability to reason quantitatively about workflows by establishing baselines, forming hypotheses, running experiments, and measuring results.
  • Strong writing skills and ability to influence engineering teams without authority.

Responsibilities

  • Instrument engineering time spent across cycle time, review latency, continuous integration failures, test authoring, operational toil, and onboarding; rank bottlenecks by recoverable hours.
  • Choose whether artificial intelligence, automation, conventional software, or process change best addresses each bottleneck, and reject artificial intelligence when it is not appropriate.
  • Apply artificial intelligence across the engineering lifecycle, including development and refactoring, first-pass code review, test generation and suite optimization, documentation and release notes, design analysis, migrations, debugging, incident investigation, and root-cause analysis.
  • Build engineering agents to diagnose continuous integration failures, investigate production issues, write tests, run dependency upgrades, propose security fixes, analyze pull requests, and execute repetitive migrations, using human-in-the-loop workflows by default and earning autonomy per workflow.
  • Redesign code review, testing, continuous integration, and incident management for workflows where artificial intelligence performs the first pass; define human ownership and mandatory approval points.
  • Build an engineering productivity platform with an artificial intelligence gateway, agent runtime and workflow orchestration, codebase intelligence, engineering context retrieval, Git, continuous integration, observability, and ticketing integrations, plus application programming interfaces and software development kits for teams to build workflows.
  • Provide agents permission-aware access to code, architecture documentation, service ownership, deployment state, telemetry, incidents, and standards; own retrieval quality and freshness.
  • Establish quality, security, privacy, access-control, approval, auditability, and evaluation guardrails for artificial intelligence-generated changes.
  • Baseline performance, run experiments, publish results, stop initiatives that do not improve metrics, and mentor teams in effective patterns.
  • Measure and improve cycle time, repetitive work, pull request review and continuous integration failure resolution, escaped defects, incident diagnosis, operational toil, onboarding, deployment frequency, throughput, and adoption of artificial intelligence workflows.
  • Within 90 days, baseline engineering time, quantify the leading bottlenecks in recoverable hours, and ship an automation that is in use.
  • Enable artificial intelligence workflows to perform first-pass code review, test generation, and continuous integration failure diagnosis by default, with humans reviewing judgment rather than mechanics.
  • Deliver measurable quarter-over-quarter cycle-time reductions attributable to specific changes.
  • Deploy agents that carry meaningful workload across defined workflows with approval gates, audit trails, and tracked reliability, without increasing escaped defects or security findings.

Desired Qualifications

  • Experience with large language model APIs and model orchestration.
  • Experience building production artificial intelligence agents with tool use.
  • Experience with retrieval-augmented generation, retrieval systems, and vector databases.
  • Experience with Model Context Protocol or similar tool and context protocols.
  • Experience with large language model evaluation, prompt and context engineering, and artificial intelligence observability.
  • Experience with GitHub or GitLab APIs and deep continuous integration and continuous delivery integration.
  • Experience with Kubernetes and cloud platforms.
  • Experience with internal developer platforms.
  • Experience with DORA- or SPACE-style engineering measurement.
  • Experience in security- or compliance-bound environments.

About the Company

Safe Security

AI-powered cybersecurity risk analytics platform

Safe.Security provides a real-time cyber risk management platform for businesses. It collects and analyzes millions of signals per customer per day using AI to give a live view of an organization's risk posture. The platform connects with 50+ APIs, threat feeds, and user data, uses a Generative AI interface called SafeGPT, and maps risk across the MITRE ATT&CK kill chain to show where an attack could happen. It helps translate security controls into financial exposure for underwriting and guides which security investments to prioritize, with the broader goal of aligning cybersecurity risk with enterprise risk and securing appropriate cyber insurance.

Company size
501-1,000
Company stage
Series C
Total funding
$162.2M
Headquarters
Palo Alto, CA
Founded
2012

Recently Posted Jobs

Explore more opportunities at Safe Security

See more jobs