M

Metaforms

AI-driven qualitative research interview platform

Senior AI Engineer

AI Application EngineeringConfirmed live in the last 24 hours
Full-timeBengaluru, Karnataka, IndiaNo salary listedIn-person

About the Job

Requirements

  • Candidates must have built and operated agentic systems in production, including multi-step pipelines, tool use, code generation, computer use, or data and reporting agents, rather than only prototypes.
  • Candidates must have at least 4 years of engineering experience, including at least 1 year focused on production large language model or agent systems.
  • Candidates must have hands-on experience with frontier model application programming interfaces, including Anthropic, OpenAI, or Gemini, as well as evaluation frameworks and artificial intelligence system optimization.
  • Candidates must have strong Python skills; Go or TypeScript is a plus.
  • Candidates must understand context engineering and evaluation methodology.
  • Candidates must be able to debug complex, non-deterministic system failures and independently drive problems to resolution.

Responsibilities

  • Own the production agent harness where agents plan, use tools, check their work, and recover from failures.
  • Lead research and implementation for long-context handling and cascading-error challenges in multi-step agent pipelines.
  • Drive context engineering strategy and experimentation frameworks across the team.
  • Define structured rubrics for evaluating artificial intelligence outputs on nuanced, ambiguous research tasks.
  • Build continuous monitoring, tracing, and failure-mode analysis for production agents, including the process that turns production failures into test cases.
  • Create tooling that allows domain experts to refine and evolve the skill files, evaluation sets, and knowledge bases consumed by agents.
  • Build evaluation suites, including regression sets, golden datasets, and large language model-as-judge pipelines, to catch regressions before deployment.
  • Develop evaluation datasets for domain-specific languages, structured data transformations, and computed outputs to systematically identify and address model weaknesses.
  • Design human-in-the-loop and review workflows for outputs where an incorrect number in a client report is unrecoverable.

Desired Qualifications

  • Experience with large language model observability and evaluation tooling such as Braintrust, Langfuse, LangSmith, Weave, promptfoo, or equivalent in-house tools.
  • Background in semantic parsing, domain-specific languages, or structured-output generation.
  • Prior experience with computer-use or browser agents.
  • Experience with human-in-the-loop agent workflows in which proposals are reviewed before application, or with agents operating over large structured datasets.

About the Company

Metaforms

AI-driven qualitative research interview platform

Metaforms.ai provides an AI-driven platform for qualitative research that helps organizations plan and run interviews, observations, and focus groups to uncover deep insights about people and processes. The platform supports interviewer deployment, enables exploration of organizational culture, employee experiences, and decision-making, and integrates with usability testing, contextual inquiries, and diary studies through connections with other tools. It uses a subscription-based pricing model with tiered plans that grant different levels of access and features. Data privacy and regulatory compliance are central, making it suitable for educational institutions, health sciences, and businesses across sectors that need careful, privacy-minded qualitative research. The goal is to deliver actionable, nuanced user and organizational insights to inform design improvements, strategy, and decision-making.

Company size
51-200
Company stage
Early VC
Total funding
$11.1M
Headquarters
Noida, India
Founded
2019

Recently Posted Jobs

Explore more opportunities at Metaforms

See more jobs