AI Engineer
Onit (company site, opens in a new tab)PuneHybridDirect career pageEst. 18–35 LPA
Posted 8d ago
Reach people at Onit
People at this company you can reach
Log in to see who works here
Create a free account or log in to see the people at Onit you could write to:
- Recruiters & HR
- People in this function
- Work addresses
Your match
Against your primary resume
Log in to see your match score
Create a free account or log in to unlock your CV match score across:
- Role fit
- Experience
- Industry relevance
Protocol Intelligence
How competitive this role is
Competition
Background fit
Strictness
Log in to see why each signal reads the way it does.
Job description
Structured overview of role & requirements
About This Role
- Design, build, and own agentic AI features and workflows using LLM APIs and multi-agent architectures, focusing on document understanding, reasoning, and task automation.
- Establish and maintain evaluation frameworks including automated pipelines, regression testing, and online metrics to ensure AI output quality and safety.
- Develop scalable backend AI services with observability, reliability, and secure integration into cloud and microservice architectures, partnering cross-functionally on AI-first product solutions.
Minimum Requirements
- Experience building and shipping backend AI systems with hands-on work on agentic LLM architectures including agent loops, tool interfaces, memory/state management, failure handling, and context engineering.
- Strong software engineering skills with Python preferred and practical experience using LLM APIs from providers like OpenAI, Azure OpenAI, Anthropic, or Gemini.
- Proven ability to create evaluation suites (golden datasets, adversarial cases) and implement automated evaluation pipelines and monitoring systems.
- Work Experience Required: Not explicitly mentioned in the JD.
Ideal Candidate Profile
- Has successfully launched one or more LLM-based agent systems in production with deep knowledge of failure modes, evaluation strategies, and cost/latency tradeoffs.
- Demonstrates strong systems thinking and debugging skills and comfort operating in fast-paced, ambiguous environments with high ownership.
- Possesses familiarity with cloud platforms, microservices, observability tools, workflow orchestration, and AI safety/governance best practices (nice to have but signals stronger candidacy).