AI Engineer

In this role, you will design, build, and deploy Generative AI solutions, LLM-powered applications, retrieval-augmented generation (RAG), and agentic workflows integrated with enterprise data and systems. Working alongside senior engineers and in close collaboration with product, engineering, and security partners, you'll help deliver reliable, scalable, and safe GenAI capabilities, with a focus on evaluation, observability, and cost/latency performance in production.

Responsibilities:

• Design and implement LLM-powered conversational experiences, including chat assistants and AI agents, integrating tools, APIs, and enterprise data sources.
• Build and maintain RAG pipelines, including document ingestion, chunking, embeddings, and indexing, using vector databases and AI-enabled search.
• Develop LLM inference and orchestration components such as prompt templates, function and tool calling, streaming, and caching that meet defined latency and reliability targets.
• Implement safety and compliance guardrails, including content filtering, prompt injection defenses, and data access controls, and support red-teaming and testing of GenAI applications.
• Help optimize GenAI solutions for cost and performance, including token usage, prompt compression, caching, and model routing, while maintaining response quality.
• Apply responsible AI practices for GenAI, including grounding, hallucination mitigation, privacy-by-design, and bias/toxicity evaluation, and align with security requirements.
• Document designs, prompts, evaluation results, and operational runbooks, and contribute reusable components and code that the wider team can build on.

Requirements:

• BE/BTech in Computer Science, Data Science, Engineering, or a related field, or equivalent practical experience.
• 3-5 years of total experience as a software engineer, including hands-on experience building and shipping AI/ML and GenAI solutions such as LLMs, RAG, and prompt/tool calling using Python.
• Strong programming skills in Python and experience building LLM applications using common frameworks such as LangChain and LangGraph; familiarity with evaluation and testing frameworks is a plus.
• Hands-on experience deploying GenAI applications on cloud platforms such as GCP, Azure, or AWS, including integration with managed LLM services and secure API patterns.
• Experience with vector databases and retrieval systems such as Pinecone, Milvus, Weaviate, and Elasticsearch/OpenSearch; exposure to LLMOps tooling for prompt/version management and evaluation is a plus.
• Working knowledge of CI/CD and familiarity with observability for GenAI systems, including quality and safety metrics, tracing, and monitoring latency and cost.
• Working knowledge of Agile delivery and collaboration tools such as Jira and Confluence, with the ability to clearly communicate technical work and trade-offs to the team.
• Strong analytical and problem-solving skills to debug GenAI issues such as grounding gaps, hallucinations, prompt injection, and retrieval quality across application, data, and infrastructure layers.

Nice To Have:

• Experience with Node, React, Terraform, Git, GitLab, Docker, and Kubernetes.

Skills

LLM, LLMs, Python, RAG, large language model, large language models, retrieval augmented generation