Senior Software Engineer

About the job

Description : Responsibilities : - Lead the design, development, and deployment of production-grade AI and LLM-powered solutions using Python and Golang. Architect and implement scalable backend services and APIs in Golang to serve AI/ML models with high performance and reliability. - Build and optimize RAG (Retrieval Augmented Generation) pipelines using vector databases, embeddings, and advanced retrieval strategies. - Design and implement sophisticated prompt engineering strategies, including few-shot learning, chain-of-thought prompting, and context optimization for LLM applications. - Work with LLMs (GPT-4 Claude, Llama, etc.) to build intelligent systems for text generation, analysis, classification, and reasoning tasks. - Develop microservices and data processing pipelines in Golang and Python to handle high-volume data ingestion, transformation, and model inference. - Design and implement embedding strategies for semantic search, similarity matching, and knowledge retrieval systems. - Build and maintain vector databases (Qdrant, Pinecone, Weaviate, etc.) for efficient similarity search and retrieval. - Optimize model performance, latency, and cost for production deployments across cloud environments. - Write clean, maintainable, and well-tested code with comprehensive documentation and version control practices. - Mentor junior team members and conduct code reviews to maintain high engineering standards. - Collaborate with cross-functional teams to translate business requirements into technical solutions. Requirements : - 5 - 6+ years of experience in software engineering, data science, or AI/ML engineering roles. - Expert-level proficiency in Python with a deep understanding of modern libraries (Pandas, NumPy, FastAPI/Flask, asyncio). - Strong proficiency in Golang with experience building production-grade microservices, REST APIs, and concurrent systems. - Deep understanding of LLM architectures, capabilities, and limitations with hands-on experience using OpenAI, Anthropic, Hugging Face, or similar platforms. - Proven expertise in prompt engineering techniques, including context management, system prompts, and optimization strategies for various use cases. - Strong knowledge of RAG architectures, including chunking strategies, retrieval methods, and context management. - Deep understanding of embeddings (text, multimodal), vector databases, and semantic search principles. - Proficient in SQL with experience in database design, optimization, and working with both relational and vector databases. - Experience with model fine-tuning, evaluation metrics, and A/B testing of AI systems. - Strong system design skills with the ability to architect scalable, fault-tolerant AI-powered applications. - Self-driven, with the ability to own projects end-to-end and deliver production-quality solutions. Bonus points if you have : - Experience building and deploying production RAG systems at scale. - Familiarity with LangChain, LlamaIndex, or similar LLM orchestration frameworks. - Experience with advanced prompting techniques such as ReAct, Tree of Thoughts, or multi-agent systems. - Knowledge of model deployment and serving frameworks (vLLM, TGI, Triton). - Experience with distributed systems and message queues (Kafka, RabbitMQ, Redis). - Exposure to Kubernetes, Docker, and cloud platforms (AWS, GCP, Azure). - Understanding of LLM fine-tuning techniques (LoRA, QLoRA, PEFT). - Experience with monitoring, observability, and LLM ops tools (LangSmith, Weights and Biases). - Contributions to open-source AI/ML projects or technical writing/speaking experience. - Familiarity with graph databases (Neo4j) for knowledge graph applications. (ref:hirist.tech)

Requirements

• Python
• Golang
• LLM architectures
• RAG architectures
• SQL

Preferred Technologies

• Python
• Golang
• LLM architectures
• RAG architectures
• SQL

About the company

Hirelo specializes in developing advanced AI solutions, particularly in the areas of AI and ML applications. They focus on deploying production-grade AI and LLM-powered solutions for various industry use cases.