AI Application Engineer

As an AI Application Engineer at Rearc in Pune, India, you will be instrumental in advancing our machine learning and artificial intelligence capabilities. Your expertise will be crucial in designing and deploying efficient, reliable, and production-ready intelligent systems, with a focus on Machine Learning, AI application development, and LLMOps. You will collaborate with cross-functional teams to build and operationalize Generative AI (GenAI) solutions, pushing the boundaries of AI in customer environments. Success in this role requires building strong partnerships with technical teams and stakeholders, aligning with business objectives, and supporting AI-driven initiatives through to successful execution.

Key Responsibilities:

• Collaborate closely with colleagues to understand client business objectives and technical challenges, contributing to the design and development of effective GenAI solutions tailored to specific needs.
• Apply GenAI principles and utilize modern tools and frameworks, such as LangGraph, to construct scalable, reliable, and maintainable Compound AI systems, ensuring adherence to rigorous industry and ethical standards.
• Continuously research, learn, and stay updated with the latest advancements and state-of-the-art techniques in AI application development.
• Promote knowledge sharing through blog posts, articles, and internal talks, reinforcing a culture of continuous learning and fostering shared expertise and innovation across the engineering community.

What You Bring:

Experience:

• A minimum of 2 years of experience in AI engineering, machine learning (ML), or related fields, with a proven track record in building and deploying intelligent systems.

Generative AI (GenAI) Expertise:

• A strong understanding of state-of-the-art generative AI techniques, including large language models (LLMs), text generation, and other foundation models.
• Familiarity with AI orchestration tools such as LangGraph, CrewAI, Bedrock Agents, and smolagents.
• Experience in fine-tuning, prompt engineering, or adapting generative models for specific use cases.
• Proficiency in AI model evaluation, including human-in-the-loop and LLM judge paradigms.
• Familiarity with Natural Language Processing (NLP) libraries and frameworks.

Knowledge Base & Tool Integration:

• Hands-on experience implementing Retrieval Augmented Generation (RAG) architectures and integrating retrieval systems with generative models.
• Knowledge of at least one vector store or database (e.g., Opensearch, Pinecone, PostgreSQL with pgvector) and techniques for similarity search.
• Familiarity with common data ingestion/ETL patterns for populating knowledge bases.
• Experience implementing LLM tool calling, either directly, via an orchestration framework, or using Model Context Protocol (MCP) clients.

Amazon Bedrock or Databricks AI Experience:

• Experience using Amazon Bedrock or Databricks Mosaic AI for deploying and managing generative AI models.
• Ability to integrate Generative AI scripts with other services (e.g., AWS S3, Lambda, or Databricks Apps) to build scalable and secure AI solutions.

Software & Tools Proficiency:

• Strong programming skills in Python or similar languages.
• Familiarity with CI/CD pipelines and MLOps practices for seamless integration, testing, and deployment of AI models.

Nice-to-Haves:

• Experience with containerization and orchestration for deploying AI services.
• Understanding of cloud security best practices and cloud architecture design for AI workloads.
• Experience writing MCP servers.
• Experience training or fine-tuning ML models (classical ML or LLMs/diffusion models).