Senior Prompt Engineer
HTC Global Services
About the Role:
We are seeking a highly skilled AI Engineer /Prompt Engineering, to design, develop, and deploy enterprise-scale AI solutions that solve complex business problems across the organization. This role will focus on Generative AI, Large Language Models (LLMs), Prompt Engineering, Agentic AI systems, Machine Learning, Data Science.
The ideal candidate will have strong hands-on experience in building intelligent applications end to end, including data preparation, model development, prompt design and optimization, orchestration of agentic workflows, deployment automation, infrastructure provisioning, monitoring, and production support. This role requires close collaboration with business stakeholders, data teams, architects, platform teams, and engineering partners to rapidly advance AI adoption in a secure, scalable, and business-aligned manner.
Responsibilities
- Design, develop, and deploy enterprise AI solutions using LLMs, Prompt Engineering, Agentic AI frameworks, classical Machine Learning, and Data Science techniques.
- Build intelligent applications such as RAG-based systems, AI copilots, conversational assistants, autonomous or semi-autonomous agent workflows, document intelligence solutions, and NLP-driven applications.
- Design and optimize prompts for enterprise use cases, including prompt templates, chaining strategies, structured outputs, instruction tuning patterns, context control, and response optimization.
- Develop and maintain data pipelines for structured and unstructured data to support model training, retrieval, inference, analytics, and evaluation workflows.
- Implement and manage retrieval pipelines, embeddings, vector search, tool calling, memory strategies, and orchestration logic for LLM-powered applications.
- Fine-tune, evaluate, optimize, and monitor AI/ML models and LLM-based systems for performance, accuracy, explainability, scalability, reliability, and cost efficiency.
- Collaborate with business stakeholders and cross-functional teams to understand business requirements, define AI opportunities, structure hypotheses, and translate them into scalable technical solutions.
- Build and manage AI solution infrastructure on AWS, leveraging services such as S3, Lambda, EKS/ECS, API Gateway, IAM, CloudWatch, RDS, DynamoDB, OpenSearch, Bedrock, and other approved cloud services as applicable.
- Provision and manage infrastructure using Terraform/Scalr, ensuring secure, repeatable, and scalable deployments across environments.
- Implement observability, evaluation, monitoring, feedback loops, and guardrails for enterprise AI applications to ensure quality, safety, and continuous improvement.
- Partner with architecture, platform, DevOps, security, and governance teams to ensure AI solutions meet enterprise standards for security, compliance, resiliency, and operational support.
- Lead technical design discussions, code reviews, solution architecture decisions, and engineering best practices for AI application development.
- Support MLOps / LLMOps capabilities including CI/CD, model and prompt versioning, automated testing, deployment automation, runtime monitoring, and production incident response.
- Communicate technical findings, model behaviour, solution risks, and business impact clearly to leadership, stakeholders, and partner teams.
- Mentor junior engineers and data scientists while contributing to reusable frameworks, accelerators, and standards for AI engineering across the firm.
- Bachelor’s degree in computer science, Engineering, Data Science, Artificial Intelligence, or a related technical field.
- 5+ years of hands-on experience in Python and software development for AI, ML, data engineering, or cloud-based applications.
- 3+ years of experience in Machine Learning / Data Science, including feature engineering, model training, experimentation, evaluation, and deployment.
- 2+ years of experience in LLMs / Generative AI use cases such as prompt engineering, prompt optimization, RAG, embeddings, vector databases, evaluation frameworks, and guardrails.
- Strong experience with Prompt Engineering, including prompt design patterns, prompt chaining, instruction design, context-window optimization, role/task prompting, structured response generation, and prompt tuning for enterprise use cases.
- Strong understanding of Agentic AI patterns, including multi-step reasoning workflows, tool usage, memory/context handling, orchestration frameworks, and autonomous task execution.
- Strong experience with AWS cloud services for developing, deploying, and managing scalable AI/ML and data-driven applications.
- Hands-on experience with Terraform and/or Scalr for infrastructure as code and environment provisioning.
- Experience with APIs, microservices, and containerized deployments in enterprise environments.
- Experience with SQL and NoSQL databases, vector databases, and data integration across structured and unstructured sources.
- Strong knowledge of software engineering fundamentals including version control, testing, CI/CD, secure coding, code reviews, and release management.
- Experience presenting technical solutions, results, and recommendations to business stakeholders and leadership.
- Strong analytical thinking, problem-solving, communication, and cross-functional collaboration skills.
- Experience in financial services, investment management, compliance, risk, or other regulated enterprise environments.
- Experience with MLOps / LLMOps tools and practices for deployment, monitoring, evaluation, and lifecycle management of AI systems.
- Familiarity with frameworks and tools such as LangChain, LangGraph, LlamaIndex, Hugging Face, OpenAI APIs, Amazon Bedrock, MLflow, Airflow, Spark, or similar technologies.
- Experience designing and optimizing prompts for RAG workflows, agentic systems, tool calling, reasoning tasks, workflow automation, and domain-specific enterprise AI applications.
- Experience with semantic search, vector retrieval, document intelligence, conversational AI, and knowledge-grounded AI systems.
- Knowledge of Responsible AI, model governance, explainability, bias detection, risk controls, and enterprise AI safety practices.
- Experience working in Agile / Scrum delivery models.
- Experience leading or mentoring teams and driving implementation across multiple stakeholders.
- Advanced expertise in AI/LLMs with strong hands-on experience in end-to-end model development and deployment.
- Solid data engineering background with experience in building and managing complex, large-scale data systems.
- Proven ability to work effectively in large, collaborative teams within fast-paced, enterprise environments.
- Strong ownership and accountability for end-to-end delivery
- Ability to translate ambiguous business problems into practical AI solutions
- Strong collaboration across engineering, product, business, and governance teams
- Technical leadership in solution design and implementation