Senior Developer (DPO) (IN)

HCLTech

3+ yrs India Full Time Remote
HCLTech logo
Posted : today
Actively hiring

Job description

Are you a technically driven Generative AI Engineer passionate about building cutting-edge LLM applications? This hands-on role offers the opportunity to transform the latest advancements in generative AI into robust, scalable business solutions. You will focus on creating advanced Retrieval-Augmented Generation (RAG) pipelines, developing autonomous agents with reliable tool-calling, fine-tuning prompts, and deploying high-performance inference APIs using containerized microservices on AWS or Azure.

Responsibilities

Key responsibilities include designing and implementing end-to-end RAG pipelines with multi-modal parsing and semantic chunking. You'll manage and optimize vector databases for rapid similarity searches, integrating hybrid retrieval and re-ranking. Develop stateful multi-agent workflows and autonomous task execution using frameworks like LangChain. Build secure function-calling interfaces connecting LLMs to external systems and implement safeguards against agent recursion. Craft systematic prompt templates and ensure deterministic, validated output structures. Conduct parameter-efficient fine-tuning (PEFT) on open-weight models for domain-specific tasks. Develop high-throughput asynchronous backend microservices with FastAPI, optimizing streaming latency and inference throughput. Containerize applications with Docker and deploy using Kubernetes or cloud-native services. Establish automated model evaluation benchmarks and implement enterprise guardrails for AI safety. Integrate comprehensive LLM tracing, prompt versioning, and cost monitoring tools.

Qualifications

Requires a minimum of 3 years in professional software engineering or data science, with at least 1.5 years dedicated to Generative AI/LLM development. A Bachelor’s degree in Computer Science, Software Engineering, Artificial Intelligence, Data Science, or a related technical field is essential. Advanced Python programming skills, including asyncio, type hints, Pydantic, and pytest, are crucial, along with deep familiarity with PyTorch or Hugging Face Transformers. Extensive hands-on experience with GenAI frameworks like LangChain, LangGraph, and LlamaIndex, as well as commercial/open foundation model APIs, is expected. Proven ability in building and deploying production RAG architectures using vector databases is necessary. Proficiency in developing asynchronous REST APIs with FastAPI, Docker containerization, and Git-based workflows is required. Strong analytical problem-solving skills, a solid understanding of transformer architecture, and proactive technical curiosity are core competencies.

Essential Skills

PythonPyTorchHugging Face TransformersLangChainLangGraphLlamaIndexOpenAI APIAnthropic APIAWSAzureFastAPIDockerGitRAGVector DatabasesLLM

Good to Have

PineconeQdrantChromaWeaviatepgvectorAzure AI SearchCohere RerankBGEAutoGenPydanticInstructorGuidanceOutlinesLoRAQLoRALlama 3MistralPhi-3Phi-4TensorRT-LLMOllamaKubernetesECSEKSContainer AppsRagasTruLensDeepEvalNeMo GuardrailsLlama GuardAzure Content SafetyLangfusePhoenixWeights & Biases

Highlights

  • Actively hiring

More Details

RoleSenior Developer (DPO) (IN)
DepartmentSoftware Development, AI / Machine Learning
Employment TypeFull Time, Remote

About the Company

HCLTech logo

HCLTech

IT Consulting

Senior Developer (DPO) (IN) at HCLTech | SkillMX | SkillMX