Synapse XTL
Website:
thesynapses.com
Job details:
We are seeking a Senior ML Engineer to lead the development and optimization of our AI systems powered by large language models. You will design RAG pipelines, fine-tune LLMs for domain-specific use cases, and build production-grade AI features that drive our voice AI platform. This is a hands-on role requiring deep expertise in modern LLM tooling, prompt engineering, and scalable ML architectures.
Experience: 5+ years
Location: Mumbai
Key Responsibilities:
- Design, build, and optimize Retrieval-Augmented Generation (RAG) pipelines for real-time knowledge retrieval and response generation.
- Develop and refine prompt engineering strategies across multiple LLM providers (GPT-4, Claude, Llama) for accuracy, consistency, and safety.
- Fine-tune and adapt open-source and proprietary LLMs for domain-specific voice AI applications.
- Build and maintain LLM orchestration workflows using LangChain, LlamaIndex, or equivalent frameworks.
- Design evaluation frameworks to benchmark model quality, latency, cost, and safety metrics.
- Collaborate with backend engineers to deploy models as low-latency, production-ready inference services.
- Stay current with rapid advances in LLM research and integrate state-of-the-art techniques into the platform.
- Mentor junior ML engineers and establish best practices for experiment tracking and model versioning.
Requirements:
- 5+ years of professional experience in machine learning or AI engineering roles.
- Strong hands-on experience with LLM prompt engineering, fine-tuning, and evaluation techniques.
- Production experience building RAG architectures with vector databases (Pinecone, Weaviate, Chroma, pgvector).
- Proficiency with LangChain, LlamaIndex, or similar LLM orchestration frameworks.
- Experience working with GPT-4, Claude, Llama, Mistral, or other frontier and open-source models.
- Strong Python programming skills and familiarity with ML tooling (PyTorch, Hugging Face, Weights & Biases).
- Understanding of embedding models, semantic search, and reranking strategies.
- Excellent communication skills and ability to translate complex ML concepts for cross-functional stakeholders.
Nice to Have:
- Experience with voice AI, ASR (Whisper, Deepgram), or TTS systems.
- Familiarity with model-serving infrastructure (vLLM, Triton, TensorRT).
- Experience with RLHF, DPO, or other alignment techniques.
- Contributions to open-source ML/AI projects or published research.
Interested ones, kindly share their resume at n.menon@thesynapses.com or apply to this post at the earliest.
Click on Apply to know more.