Principal Senior AI Engineer
encora10
This is a Principal Senior AI Engineer role at a point where AI engineering is shifting from experimental to essential. If you have deep experience building LLM systems, RAG pipelines, and production-grade AI features, this is where you move from contributor to technical leader—architecting the direction of AI-enabled products and owning them from beta to scale.
You'll design and deploy full-stack AI systems end-to-end: backend LLM orchestration and retrieval pipelines, evaluation frameworks, frontend experiences. You'll architect workflows around model selection, prompting, RAG optimization, latency, safety, and cost. You'll collaborate with Product, Design, and Engineering to define priorities and balance speed with long-term stability. You'll also identify new ways to integrate Generative AI into existing platforms and build robust cloud-native backend services and APIs.
This role expects 5+ years of experience with LLMs, RAG pipelines, TypeScript, Python, React, AWS, Node.js, AI evaluation, and prompt engineering. You should be comfortable with full-stack development and have a track record of shipping at scale.
This is an exclusive opportunity for LATAM residents only. If you meet the experience bar and want to lead AI engineering, apply through CareerJumpShip with your portfolio and relevant project examples.
About this role
Job Title: Principal Senior AI Engineer Key Skills: LLMs, RAG Pipelines, TypeScript, Python, React, AWS, Node.js, AI Evaluation, Prompt Engineering, Full-Stack Development Experience: +5 YOE Location: LATAM (Exclusive residents) We at Coforge are hiring a Principal Senior AI Engineer (21707) with the following skill set. Key Responsibilities Own and drive the technical direction for AI-enabled products and tooling, transforming AI solutions from beta to scalable production-grade platforms Design, develop, and deploy full-stack AI features end-to-end, including backend LLM orchestration, retrieval pipelines, evaluation systems, and frontend user experiences Architect and optimize AI workflows focused on model selection, prompting strategies, retrieval-augmented generation (RAG), latency, safety, scalability, and cost efficiency Identify and implement new opportunities to integrate Generative AI into existing software platforms and workflows Collaborate closely with Product, Design, and Engineering teams to prioritize features, define MVPs, and balance speed with long-term scalability Build and maintain robust backend services and APIs using modern cloud-native technologies Establish best practices for AI engineering including observability, evaluation frameworks, guardrails, testing, CI/CD, and monitoring Provide mentorship and technical leadership to engineers working on AI and platform initiatives Contribute actively to software architecture discussions and technical decision-making processes Communicate effectively with technical and non-technical stakeholders, translating business challenges into scalable engineering solutions Required Skills & Qualifications 5+ years of professional software engineering experience building and shipping production applications 2+ years of hands-on experience developing AI-enabled products using LLM APIs and Generative AI technologies Proven experience designing and implementing RAG pipelines, prompt workflows, and AI evaluation strategies Strong full-stack engineering capabilities across backend services and frontend development Proficiency in at least one statically typed programming language such as Go, TypeScript, Java, or C# Experience with modern frontend frameworks such as React and backend technologies like Node.js or Python Strong understanding of REST APIs, distributed systems, cloud-native architectures, and scalable application design Experience of working with AWS or other major cloud platforms Solid software engineering practices including testing, code reviews, CI/CD, and observability Strong problem-solving and decision-making skills, especially in ambiguous and fast-moving environments Ability to evaluate technical trade-offs related to AI solutions, including build vs. buy decisions and model optimization strategies Excellent communication and collaboration skills Preferred Skills Experience scaling AI products in startup or high-growth environments Hands-on experience with TypeScript, Node.js, React, Go, C#, Python, PostgreSQL, and AWS Experience with AI evaluation infrastructure, LLM guardrails, and observability platforms Knowledge of model fine-tuning, ML experimentation, or broader machine learning workflows Experience building developer tools, DevOps platforms, CI/CD solutions, or source-control-related products Familiarity with industrial automation, manufacturing software, IoT platforms, or operational technology environments Experience mentoring engineers and leading technical initiatives across teams Bachelor’s degree in Computer Science, Engineering, or equivalent practical experience Posted On: 06-06-2026 At Coforge, we hire professionals based solely on their skills and do not discriminate based on age, disability, religion, gender, sexual orientation, socioeconomic status, or nationality.