Ai ML Engineer

About the Role

We are looking for highly motivated AI Engineers to build and scale next-generation Agentic AI solutions powered by Large Language Models (LLMs). You will work on production-grade AI systems that leverage multi-agent architectures, Retrieval-Augmented Generation (RAG), tool integrations, memory frameworks, and model optimization techniques to solve complex business problems.

Key Responsibilities

• Design and develop multi-agent AI workflows for complex decision-making and automation use cases.
• Build and optimize RAG pipelines using structured and unstructured enterprise data.
• Develop AI agents with tool-calling capabilities for databases, APIs, CRM systems, and business applications.
• Implement memory architectures to maintain context across user interactions.
• Fine-tune and optimize open-source LLMs using LoRA/QLoRA and related techniques.
• Build evaluation frameworks to measure model accuracy, hallucinations, compliance, and business outcomes.
• Integrate AI solutions with Salesforce, SQL databases, vector stores, and internal platforms.
• Monitor and improve model performance, latency, cost efficiency, and reliability.
• Collaborate with product, engineering, and business teams to deploy scalable AI solutions.

Required Skills

Agentic AI & LLM Systems

• Multi-agent orchestration and workflow design
• RAG architectures and vector search
• Prompt engineering and tool-calling frameworks
• LangGraph, LangChain, or similar AI orchestration platforms
• LLM evaluation, testing, and observability

Model Training & Optimization

• Fine-tuning LLMs using LoRA/QLoRA
• RLHF/RLAIF concepts and feedback-driven optimization
• Hallucination mitigation and model performance tuning
• AI recommendation and decision-support systems

AI Infrastructure & Engineering

• Strong Python development skills
• FastAPI or similar backend frameworks
• Vector databases (Qdrant, Pinecone, Weaviate, etc.)
• SQL and data engineering fundamentals
• AWS services such as Bedrock, SageMaker, S3
• API integrations, Docker, and scalable deployment architectures

Preferred Qualifications

• Experience building and deploying production-grade AI applications.
• Familiarity with Llama, Mistral, DeepSeek, OpenAI, Anthropic, or similar LLM ecosystems.
• Experience with AI monitoring, evaluation, and governance frameworks.
• Strong problem-solving skills and ability to work in a fast-paced environment.