AI/ML Engineer (Agentic Systems)
Intangles (company site, opens in a new tab)1–2 yrsPuneOn-siteDirect career pageEst. 6–14 LPA
Posted 4d ago
Reach people at Intangles
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 Intangles 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
- Build and improve LLM agents that use tools, memory, and multi-step workflows; implement scoped components with guidance from senior engineers.
- Develop agent workflows, RAG pipelines, guardrails, evaluations, and tracing to improve reliability and make failures diagnosable.
- Compare models and prompts on quality, latency, and cost, and integrate agents with internal systems and APIs.
Minimum Requirements
- Work Experience Required: 1–2 years in software engineering, ML, or applied AI work.
- Bachelor’s or Master’s degree in Computer Science, AI/ML, or a related field, or equivalent practical experience.
- Strong Python skills, including Git, testing, and clean code; hands-on LLM API experience and working knowledge of prompting, structured outputs, and tool/function calling.
- Basic RAG and vector database knowledge, plus familiarity with REST APIs and basic cloud concepts. Location: Pune.
Ideal Candidate Profile
- Has practical experience building LLM applications and can contribute to agent workflows, tool integrations, and RAG components.
- Can test and refine agent quality using evaluations, experiments, guardrails, and tracing—not just write prompts.
- Fits a junior-level role with scoped ownership and senior engineering guidance; agent/LLM projects, observability exposure, or Docker/CI/CD familiarity are preferred signals.