Senior Prompt Engineering Jobs in Boston, MA (NOW HIRING)

Job Summary:
Saviance is a technology consulting firm specializing in AI/ML and data engineering. They are seeking a highly skilled Senior Software Engineer with expertise in AI and Data Engineering to contribute to technical execution, team success, and cross-functional collaboration while focusing on Generative AI and AI-enhanced workflows.
Responsibilities:
• Contribute to clear and precise technical design specifications, focusing on GenAI system integration and AI-driven workflows.
• Deliver high-quality AI-powered components and services while ensuring security, performance, scalability, and automation best practices.
• Estimate development tasks in story points, factoring in LLM inference latency and API rate limits.
• Adhere to coding conventions, architectures, and best practices for GenAI applications, prompt engineering, and RAG models.
• Write, debug, and deploy production-ready code, ensuring quick fixes for GenAI APIs, embeddings, and microservices.
• Integrate and optimize tools/frameworks such as OpenAI, Azure OpenAI, Hugging Face, LangChain, and LlamaIndex.
• Utilize vector databases ( Pinecone, FAISS, ChromaDB) for similarity search and retrieval pipelines.
• Meet sprint "Definition of Done (DOD)” including:
• Unit and functional testing
• LLM benchmarking (BLEU, ROUGE, cosine similarity)
• Model validation & API optimization (temperature, top-k, tokens)
• Code reviews, bug fixes, and documentation
• Responsible AI & governance compliance
• Learn domain-specific AI applications in automation, search, and decision support.
• Own AI-driven product features with ongoing model improvement and fine-tuning.
• Actively engage in agile ceremonies with an AI-first mindset.
• Volunteer for GenAI-related backlog items, such as:
• RAG model refinement
• Prompt engineering enhancements
• LLM evaluation and response tuning
• Participate in scrum (stand-ups, sprint planning, retrospectives) with focus on iterative AI model scaling.
• Promote self-organization and effective GenAI adoption across teams.
• Work closely with Technology, Product, AI/ML, and DevOps teams to align AI solutions with business outcomes.
• Partner with AI engineers, data scientists, and cloud architects to optimize LLM-based solutions.
• Ensure compliance with AI governance, privacy, HIPAA, GDPR, SOC2, and ethical AI standards.
• Train and mentor developers on GenAI integration, API usage, embeddings, and vector search.
• Guide team members in prompt engineering, RAG optimizations, and API latency improvements.
• Encourage use of AI-powered developer workflows (Copilot, AI-driven testing, code generation).
Qualifications:
Required:
• 5–10 years in engineering roles with exposure to AI/ML.
• Bachelor's degree (or equivalent) in Computer Science, Engineering, or related field.
• Strong background in software engineering with AI/GenAI model integration.
• Proficiency in Python (preferred for AI work).
• Familiarity with Unix/Linux, Big Data, SQL, NoSQL, and AI pipelines.
• Hands-on experience with OpenAI GPT, Hugging Face Transformers, LangChain, LlamaIndex.
• Exposure to RAG models, embeddings, similarity search, and vector databases (FAISS, Pinecone, ChromaDB).
• Experience deploying AI solutions on AWS or Azure OpenAI.
• Strong knowledge of AI evaluation metrics (BLEU, ROUGE, BERT Score, cosine similarity).
• Strong ability to design and implement AI-powered solutions that enhance software functionality.
• Analytical problem-solver skilled in debugging and optimizing AI-generated responses.
• Collaborative mindset to work across engineering, DevOps, and AI/ML functions.
• Deep knowledge of AI-driven feature development, prompt engineering, and embedding optimizations.
• Capable of evaluating AI outputs for bias, accuracy, and compliance.
• Curious, eager to explore new AI models, frameworks, and best practices for scalable GenAI deployment.
Preferred:
• Agile environment experience preferred.
Company:
Saviance is a modern consulting firm providing a variety of professional services to its clients in the US. Founded in 1999, the company is headquartered in Metuchen, USA, with a team of 201-500 employees. The company is currently Growth Stage.