GenAI Engineer

Soul AI is seeking a talented Generative AI Engineer to join our client's team in Hyderabad. In this role, you will be instrumental in building advanced intelligent systems powered by large language models (LLMs) and other generative AI architectures. Your responsibilities will include developing and deploying LLM-based features, integrating vector search capabilities, fine-tuning models, and collaborating closely with product and engineering teams to deliver robust and scalable GenAI applications. You will work across the entire GenAI stack, from prompt design to inference optimization, and play a key role in shaping the real-world application of generative models.

Responsibilities:

• Fine-tune and deploy LLMs (e.g., GPT, LLaMA, Mistral) utilizing frameworks such as Hugging Face Transformers or LangChain.
• Construct and optimize Retrieval-Augmented Generation (RAG) pipelines, incorporating vector databases like Pinecone or FAISS.
• Engineer effective prompts to ensure structured and reliable outputs across various use cases, including chatbots, summarization, and coding copilots.
• Implement scalable inference pipelines and optimize for latency, throughput, and cost using techniques such as quantization or model distillation.
• Collaborate with product, design, and frontend teams to seamlessly integrate GenAI capabilities into user-facing features.
• Monitor, evaluate, and continuously enhance model performance, safety, and accuracy in production environments.
• Ensure adherence to privacy, safety, and responsible AI practices, including content filtering and output sanitization.

Required Skills:

• Proficiency in Python programming and familiarity with modern ML tooling.
• Hands-on experience with LLM frameworks like Hugging Face Transformers, LangChain, or LlamaIndex.
• Demonstrated experience building or deploying RAG pipelines, including managing embeddings and vector search.
• Solid understanding of transformer models, prompt engineering techniques, and tokenization strategies.
• Experience working with APIs from providers such as OpenAI, Anthropic, or Cohere, and model serving using FastAPI or Flask.
• Proficiency in deploying ML models using containerization technologies like Docker and Kubernetes, or cloud services (AWS/GCP/Azure).
• Comfort with ML model evaluation, monitoring, and troubleshooting inference pipelines.

Nice to Have:

• Experience with multimodal models (e.g., diffusion models, text-to-speech, image/video generation).
• Knowledge of Reinforcement Learning from Human Feedback (RLHF), safety alignment, or model fine-tuning best practices.
• Familiarity with open-source LLMs (e.g., Mistral, LLaMA, Falcon, Mixtral) and optimization techniques (LoRA, quantization).
• Experience with LangChain agents, tool usage, and memory management.
• Contributions to open-source GenAI projects or published generative AI demos/blogs.
• Exposure to frontend technologies like React/Next.js for prototyping GenAI tools.

Educational Qualifications:

Bachelor's or Master's degree in Computer Science, Artificial Intelligence, Machine Learning, Data Science, or a related technical field is preferred. Candidates with significant relevant project experience or open-source contributions will be considered regardless of formal degree.