About the Role
We are looking for a passionate AI Engineer to join our growing team. You will design, build, and deploy large language model (LLM) powered applications and autonomous agentic systems that solve real-world problems. This role sits at the intersection of applied AI research and production engineering — you will move fast, ship intelligent systems, and push the boundaries of what’s possible with modern AI.
Key Responsibilities
LLM Integration & Prompt Engineering
- Design and integrate LLM-powered features using OpenAI, Anthropic Claude, and open-source model APIs
- Craft, iterate, and systematically evaluate prompts for accuracy, safety, and cost-efficiency
- Implement structured output parsing, function calling, and tool-use workflows
Agentic Pipeline Development
- Build multi-step agentic workflows using frameworks such as Adk,LangChain, LlamaIndex, CrewAI, or AutoGen
- Architect multi-agent systems with clear role separation, task delegation, and coordination logic
- Implement memory systems (short-term, long-term, episodic) to enable persistent agent behavior
RAG & Knowledge Systems
- Design and maintain Retrieval-Augmented Generation (RAG) pipelines from ingestion to generation
- Work with vector databases (Pinecone, Weaviate, Chroma, pgvector) for semantic search and retrieval
- Optimize chunking strategies, embedding models, and re-ranking to maximize retrieval quality
Evaluation & Observability
- Define and track metrics for LLM output quality, latency, cost, and reliability
- Set up evaluation frameworks (RAGAS, LangSmith, custom harnesses) to benchmark system performance
- Monitor production AI systems and debug regressions or hallucinations proactively
Required Skills & Experience
- 2+ years of hands-on experience building and shipping AI / ML applications in production
- Proficiency in Python with strong command of async patterns and API integration
- Practical experience with LLM frameworks: LangChain, LlamaIndex, or equivalent
- Experience building agentic systems with CrewAI, AgentAdk,AutoGen, LangGraph, or similar orchestration tools
- Familiarity with OpenAI and/or Anthropic APIs including tool use and streaming
- Working knowledge of vector databases and embedding-based retrieval systems
- Understanding of RAG architecture patterns and their trade-offs
- Solid grasp of prompt engineering techniques: chain-of-thought, few-shot, self-consistency
Nice to Have
- Experience with the Anthropic Claude API and Claude’s tool-use / function-calling features
- Familiarity with agent memory architectures (MemGPT, Zep, custom solutions)
- Exposure to evaluation frameworks such as RAGAS, TruLens, or DeepEval
- Knowledge of LLM security: prompt injection, jailbreak mitigations, guardrails
- Contributions to open-source AI projects or published experiments / blog posts
- Experience deploying AI services on AWS, GCP, or Azure using containers / serverless
Qualifications
- Bachelor’s or Master’s degree in Computer Science, AI, Data Science, or a related field — or equivalent practical experience
- 2+ years of professional experience in AI/ML engineering or applied NLP
- Portfolio of shipped projects involving LLMs or intelligent systems (GitHub, demos, or case studies)
- Strong communication skills — you can explain complex AI concepts to non-technical stakeholders
Pay: ₹400,000.00 - ₹1,100,000.00 per year
Benefits:
- Flexible schedule
- Paid sick time
- Provident Fund
Experience:
- LLMs : 2 years (Required)
- Agentic Frameworks: 2 years (Required)
- RAG Systems: 2 years (Required)
Work Location: Hybrid remote in Bengaluru, Karnataka
