Gen AI Developer

We are seeking a highly skilled and motivated LLM / AI Developer with 2 to 4 years of relevant experience to join our innovative team. The successful candidate will be instrumental in designing, developing, and deploying cutting-edge LLM-powered solutions specifically tailored for HealthTech use-cases. This role requires a professional with hands-on experience in Python, a deep understanding of RAG pipelines, expertise in tool/function calling agents, and practical knowledge of local embeddings and local LLM deployment using platforms like Ollama. Exposure to cloud AI services is also highly valued.

Key Responsibilities

Design and implement robust LLM-based solutions, including chat agents, sophisticated tool-calling workflows, summarization, extraction, transcription services, and advanced Retrieval-Augmented Generation (RAG) systems.

Build end-to-end RAG pipelines, encompassing ingestion, intelligent chunking strategies, embedding generation, efficient retrieval mechanisms, reranking algorithms, and context-aware generation with verifiable citations.

Develop and deploy secure tool calling / function calling agents capable of seamless interaction with various APIs, databases, and internal proprietary tools.

Work with ETL (Extract, Transform, Load) pipelines to effectively normalize and preprocess diverse healthcare documents, including PDFs, scanned documents, text files, and structured data formats.

Utilize and experiment with platforms such as Ollama, llama.cpp, and Hugging Face Transformers for model experimentation, fine-tuning (as required), and efficient deployment of LLMs.

Establish and manage local embedding pipelines, ensuring optimal performance and seamless integration with leading vector databases like pgvector, Qdrant, or FAISS.

Integrate and optimize AI models with major cloud AI services, including AWS and Azure, as project requirements dictate.

Develop and manage scalable APIs and robust data pipelines for AI solutions using modern frameworks such as FastAPI or Flask.

Leverage Linux CLI and Docker for streamlined deployment, automation, and continuous monitoring of AI applications.

Collaborate closely with engineering and product teams to deliver high-quality, production-ready AI applications that meet business objectives and user needs.

Required Skills & Qualifications

Strong proficiency in Python programming.

Extensive experience with Linux CLI and practical knowledge of deployment workflows.

Hands-on expertise in developing and implementing LLM systems, including RAG architectures, embedding techniques, and advanced prompt engineering.

Demonstrated experience with Ollama (or similar local LLM inference stacks) and Hugging Face Transformers library.

Solid understanding of vector search, embeddings, and retrieval optimization strategies.

Proven knowledge of ETL processes and data normalization techniques, particularly in handling diverse data types.

Familiarity with AWS/Azure AI services is considered a significant advantage.

Strong understanding of Natural Language Processing (NLP) tasks such as summarization, transcription, information extraction, and generative AI principles.

Exceptional problem-solving abilities and a genuine passion for applied AI and its real-world applications.

What We Offer

A competitive salary and comprehensive benefits package.

Significant opportunities for professional development and accelerated career growth within a rapidly evolving field.

A collaborative, inclusive, and supportive work environment that fosters innovation.

Direct exposure to cutting-edge LLM and Health Tech AI projects, making a tangible impact on healthcare.

If you are passionate about technology and eager to work in a collaborative environment, we would love to hear from you!