Job Summary
The senior AI engineer will design, develop, integrate, and optimize production-grade AI and LLM-powered solutions for the organization. The role requires strong expertise in LLM applications, RAG, embeddings, vector search, AI agents, tool/function calling, structured outputs, summarization, sentiment analysis, information extraction, and production AI integration, with strong capabilities in LLM evaluation, latency, and cost optimization.
The ideal candidate will have experience building production SaaS products, preferably in AR, collections, fintech, ERP, or AI automation, and be comfortable working in an early-stage/startup environment. The candidate must demonstrate strong ownership, the ability to build features end-to-end, and good testing, documentation, and engineering practices.
Key Responsibilities
LLM Application Development
- Design and implement production-grade LLM applications.
- Integrate commercial and/or open-source LLMs.
- Develop structured AI workflows.
- Implement prompt engineering and prompt management.
- Develop reliable AI-powered business processes.
RAG & Knowledge Systems
- Design RAG architectures.
- Implement embeddings and vector search.
- Develop document ingestion pipelines.
- Optimize retrieval quality.
- Implement chunking, indexing and metadata strategies.
- Evaluate retrieval accuracy.
AI Agents
- Develop AI agents.
- Implement tool/function calling.
- Design agent workflows.
- Integrate external APIs and business systems.
- Implement structured outputs.
- Develop guardrails and fallback mechanisms.
AI Use Cases
- Summarization
- Sentiment analysis
- Information extraction
- Classification
- Document processing
- Intelligent automation
- Conversational AI
- Customer communication automation
AI Productionization
- Integrate AI services with backend systems.
- Develop scalable AI APIs.
- Monitor model performance.
- Optimize latency and token consumption.
- Control AI infrastructure costs.
- Implement AI observability.
AI Evaluation & Governance
- Build LLM evaluation frameworks.
- Develop test datasets and benchmarks.
- Monitor hallucination and accuracy.
- Implement prompt/model regression testing.
- Establish AI quality metrics.
- Support responsible and secure AI deployment.
Experience
- 5–8+ years of software/AI/ML engineering experience.
- 2–3+ years of practical LLM/Generative AI experience.
- Demonstrable experience deploying AI solutions into production.
- Experience with RAG and vector databases.
- Experience integrating AI into backend systems.
Pay: From ₹50,000.00 per month
Application Question(s):
- What is the notice period to join?
- What is your salary expectation?
- Do you have experience in RAG and vector databases?
- Do you have experience integrating AI into backend systems?
- How many years of experience do you have as a software/AI/ML engineering?
Work Location: Remote
