Generative AI Developer / Engineer/Analyst
5 views2-3 years
Posted 9 days ago
- .NET
- Angular
- Java
- Llm
- Node.js
- Python
- React
- Vue.js
This position is listed on behalf of a partner company, who manages all applications and next steps. Our partner is looking for a Generative AI Developer / Engineer / Analyst based in India.
We are looking for a talented Generative AI professional to design and develop production-ready applications powered by Large Language Models (LLMs). In this role, you will combine software engineering, prompt engineering, data analysis, and automation to deliver intelligent solutions that address real business challenges. You will work across the full lifecycle of AI application development, from translating requirements into generative AI use cases, building API integrations and backend components, to evaluating model outputs.
Accountabilities:
- Design, implement, and maintain Generative AI applications and components using LLMs, APIs, and modern development frameworks.
- Develop, test, and optimize prompt engineering strategies (few-shot prompting, chain-of-thought, system prompts) to maximize model accuracy, consistency, and reliability.
- Design and implement Retrieval-Augmented Generation (RAG) pipelines, integrating vector stores, semantic search, and document preprocessing workflows.
- Integrate Generative AI capabilities into existing enterprise software, internal tools, and external services via REST APIs and microservices.
- Analyze complex datasets, document structures, and business processes to identify automation opportunities and design appropriate AI-driven solutions.
- Conduct systematic evaluation and testing of LLM outputs, tracking metrics such as relevance, precision, hallucination rates, and latency.
- Collaborate with business stakeholders, product managers, and software engineers to define requirements, design workflows, and deliver end-to-end solutions.
- Implement guardrails, content filtering, and security controls to ensure responsible and compliant AI deployments.
- Document architectures, technical designs, prompts, and evaluation methodologies to support knowledge sharing and long-term maintainability.
- Stay current with advancements in foundation models, open-source LLMs, agentic frameworks, and generative AI engineering patterns.
Requirements:
- 2-3 years hands-on experience developing Generative AI or LLM-based applications in production or prototype environments.
- 1-3 years practical experience designing, testing, and optimizing prompts for LLMs (OpenAI, Anthropic, open-source models).
- 2-3 years experience in data analysis, business analysis, or analytics-focused roles, with a track record of translating business needs into technical solutions.
- Proficiency in at least one modern programming language (Python, Java, Node.js, .NET, or equivalent) with experience building backend services or data pipelines.
- Demonstrated experience building complete end-to-end applications that integrate LLMs with external APIs, databases, or user interfaces.
- Practical experience using internal, private, or enterprise LLM platforms, including deploying models, managing API access, or working within secure corporate AI environments.
- Solid understanding of RAG architectures, vector databases (such as Pinecone, Weaviate, Chroma, or pgvector), and semantic search principles.
- Experience with REST APIs, backend services, and service-oriented architectures.
- Familiarity with modern frontend frameworks such as React, Angular, or Vue is advantageous.
- Clear understanding of LLM limitations (hallucinations, bias, model drift) and proven strategies for output validation and guardrailing.
- Awareness of trade-offs between AI application costs, latency, scalability, and performance.
- Strong written English skills, essential for high-quality prompt development, system documentation, and effective cross-team communication.
- Strong problem-solving and analytical thinking skills, with the ability to navigate ambiguous requirements and identify root causes across programming, data, and business logic.
- Ability to understand business objectives, ask probing questions, and deliver technology solutions that produce measurable business outcomes.
Nice-to-have qualifications:
- Experience with Blue Prism or other RPA platforms (such as UiPath, Automation Anywhere), particularly in combining RPA bots with Generative AI capabilities.
- Experience developing and maintaining enterprise web applications or full-stack software solutions.
- Familiarity with LLMOps or MLOps concepts, including model monitoring, prompt versioning, automated evaluation, and CI/CD for AI pipelines.
- Knowledge of document-intensive business environments (such as contract management, insurance, financial services, or legal tech).
- Previous experience in regulated industries or enterprise technology environments where data privacy, security, and governance are critical considerations.
- Ability to explain complex Generative AI concepts clearly to both technical and non-technical stakeholders.
Benefits:
- Remote working flexibility: Fully remote working arrangement from India.
- Professional development: Access to continuous learning opportunities, training programs, and professional development resources.
- International career opportunities: Possibility to collaborate with global teams and explore international mobility opportunities.
- Career advancement: Opportunities to develop your technical expertise and progress professionally within an international organization.
- Learning and innovation: Exposure to modern technologies, innovative digital solutions, and industry experts.
- Collaborative culture: Work in a diverse and inclusive environment that encourages knowledge sharing, creativity, and teamwork.
- Autonomy and flexibility: A working culture that values individual contributions, initiative, and different perspectives.
- Location-specific benefits: Compensation, healthcare, and additional benefits are tailored to the employment location. Full details will be shared during the recruitment process.