Python
Amazon Web Services (AWS)Senior AI Engineer
Code Generation, Agent Architecture & LLM Systems
š Mumbai (On-site) | Full-time | 5+ years
About the Role:
Unico Connect is an AI-first technology partner that builds custom mobile, web, and AI products for clients across multiple geographies.
We are hiring a Senior AI Engineer for a dedicated client engagement focused on building an AI-powered application builder platform - a product where users describe software in plain English and the system generates, previews, and iteratively refines working code.
The mandatory requirement for this role is hands-on production experience shipping LLM-powered systems with agent architectures, with experience in code generation or developer tooling contexts a strong advantage.
The role is product-focused and deeply hands-on. You will own everything between the user's prompt and correct code landing in the project: the agentic loop, code generation pipeline, context management, evaluation suite, and model cost strategy.
You will work alongside the Senior MLOps Engineer who operationalises the infrastructure around your system, and collaborate closely with backend, frontend, and DevOps engineers.
Responsibilities:
Agent Architecture
Design and own the agentic loop for the platform - request interpretation, planning, tool-calling sequence (read file, edit file, run build, search code, install package), and stop conditions.
Make and revisit architectural decisions on single-agent vs. multi-agent designs, including planner/executor splits and dedicated build-repair sub-agents.
Code Generation Pipeline
Own the end-to-end generation flow: task classification, context gathering, planning, targeted edits, verification, and commit.
Implement diff/search-replace-based file editing with fuzzy matching and fallback strategies.
Enforce scope discipline so the agent makes minimal diffs and does not modify code it was not asked to touch.
Self-Repair Loop
Build and tune the automated repair loop that pipes compiler, lint, build, and runtime errors back to the model with retry budgets and model escalation.
This loop is the primary quality lever - the difference between 60-70% and 90%+ build success rates.
Context Management
Build file-relevance retrieval so the agent sees the right files, not the whole codebase: dependency graphs, AST/tree-sitter-based chunking, embeddings, recency signals, and hybrid retrieval.
Implement conversation summarisation and memory for long sessions, and address long-project degradation through codebase summaries and periodic consistency passes.
Own token budgeting and prompt caching strategy.
Prompt Engineering as a Discipline
Own the system prompt and per-task prompt variants (new feature, bug fix, styling change).
Maintain few-shot examples and enforce coding conventions, stack rules, and prohibited behaviours such as no hardcoded secrets and no whole-file rewrites.
Version prompts like code with changelogs and rollback capability.
Evaluation and Quality Measurement
Design and own the evaluation suite: representative test prompts run on every prompt and model change, scored on build success rate, instruction adherence, and output quality including LLM-as-judge and visual/screenshot checks where relevant.
Define regression gates that block quality-degrading changes from shipping.
Treat evals the way engineers treat automated testing: versioned, automated, and tracked over time.
This responsibility is non-negotiable at this level.
Model Strategy and Cost
Design model routing - cheap and fast models for classification and small edits, frontier models for complex generation.
Drive cost optimisation through prompt caching, diff-based edits over full-file rewrites, and tighter context selection.
Track cost per agent run and tokens per task; evaluate new model releases against the eval suite and lead migrations when results justify it.
Safety and Reliability of Agent Behaviour
Defend against prompt injection from user content and fetched web content.
Ensure secrets never appear in generated client code.
Define what the agent's tools may and may not do in collaboration with the platform team.
Contribute to output moderation and abuse-pattern awareness.
Mentorship and Engineering Standards
Run code reviews, define engineering conventions for AI work, and raise the engineering bar across the AI team.
Work closely with the Senior MLOps Engineer on handoff of eval design, prompt configurations, and model routing logic.
Requirements:
Hands-on Production Ownership of LLM-Powered Systems with Agent Architectures (Mandatory)
Must have personally shipped and operated at least one complex production AI system - agentic, multi-step, or code generation - with end-to-end ownership of architecture, evaluation, and cost.
POCs, internal demos, and tutorial-grade work do not qualify.
5+ Years of Professional Software or AI Engineering Experience
With at least 3 years focused on LLM applications, AI engineering, or production AI systems.
Candidates with strong backend backgrounds and a clear, substantive pivot into LLM systems qualify.
Strong Python Proficiency and Service Development
Production-grade Python with FastAPI or equivalent: type hints, async patterns, streaming responses, testing, and packaging.
Not notebook-only.
Depth Across LLM APIs and Agent Systems
Production experience with at least two of OpenAI, Anthropic Claude, Google Gemini, or open-weight models (vLLM, Ollama, Together).
Production experience with at least one agent framework (LangGraph, CrewAI, AutoGen, LlamaIndex Agents) or hand-rolled equivalent.
Hands-on with tool calling, structured outputs, and multi-step reasoning.
Demonstrated, Systematic Evaluation Practice - Non-Negotiable
Must have built evaluation harnesses that gate production releases, not ad-hoc testing.
Hands-on with at least one of LangSmith, Langfuse, Promptfoo, Ragas, or DeepEval.
Candidates with no systematic answer to evaluation should not be considered at senior level regardless of other strengths.
Cost Discipline for Production AI
Track record of measurable cost optimisation on production AI features.
Able to speak in specifics: cost per request, savings achieved through caching or model routing, context reduction decisions.
AWS Working Knowledge
Hands-on with EC2, S3, IAM, and Docker.
Comfort with CI/CD workflows and deploying AI services.
Awareness of LLM Security Failure Modes
Familiar with prompt injection patterns, understands that system prompt rules alone are insufficient, and has experience with output validation and content safety in production.
Nice to Have
- Experience with AST/tree-sitter tooling, diff-based editing systems, or compiler-adjacent work
- MCP server authoring
- Open-source AI contributions
- Published technical writing on LLM systems
- Multi-modal model experience
- Fine-tuning exposure (LoRA, QLoRA, PEFT)
Shubham Vishwakarma
Full Stack Developer - Averlon
About Unico Connect Private Limited
About
Building quality products are a challenge !
Taking up challenges is our way of upscaling our performance.
Unico Connect is a digital product development company based in Mumbai, India, that comprises of a team of young enthusiastic nerds who thrive on great ideas and exciting projects that look to bring innovative changes in the world. We ideate, create and execute exceptional digital products that revolutionizes the face of modern business.
Photos
Company social profiles
Similar jobs
JavaAmazon Web Services (AWS)- Develop, and maintain Java applications using Core Java, Spring framework, JDBC, and threading concepts.
- Strong understanding of the Spring framework and its various modules.
- Experience with JDBC for database connectivity and manipulation
- Utilize database management systems to store and retrieve data efficiently.
- Proficiency in Core Java8 and thorough understanding of threading concepts and concurrent programming.
- Experience in in working with relational and nosql databases.
- Basic understanding of cloud platforms such as Azure and GCPĀ and gain experience on DevOps practices is added advantage.
- Knowledge of containerization technologies (e.g., Docker, Kubernetes)
- Perform debugging and troubleshooting of applications using log analysis techniques.
- Understand multi-service flow and integration between components.
- Handle large-scale data processing tasks efficiently and effectively.
- Hands on experience using Spark is an added advantage.
- Good problem-solving and analytical abilities.
- Collaborate with cross-functional teams to identify and solve complex technical problems.
- Knowledge of Agile methodologies such as Scrum or Kanban
- Stay updated with the latest technologies and industry trends to improve development processes continuously and methodologies.
Company Description
UpSolve is a Gen AI and Vision AI startup that helps businesses solve their problems by building custom solutions that drive strategic business decisions. Whether your business is facing time constraints or a lack of resources, UpSolve can help. We build enterprise grade AI solutions with focus on increasing ROI.
Role Description
This is a full-time hybrid role for a Business Analyst located in Mumbai.
Please note: This is an onsite role and good communication skills are expected (oral + written)
Responsibilities
1. Understand existing system integrations for the client.
2. Map and identify gaps in existing systems.
3. Ideate, Advise and Implement AI Solutions to optimize business process.
4. Collaborate with multiple teams and stakeholders.
Qualifications
- MBA with focus on Business Analytics or Bachelor's degree in Computer Science or IT
- Minimum 4 Years of Experience
- Strong written, verbal and collaboration skills
- Immediate Joiner (Less than 5 days)
Work Location: Mumbai, Work from Office
Amazon Web Services (AWS)Has substantial expertise in Linux OS, Https, Proxy knowledge, Perl, Python scripting & hands-on
Is responsible for the identification and selection of appropriate network solutions to design and deploy in environments based on business objectives and requirements.
Is skilled in developing, deploying, and troubleshooting network deployments, with deep technical knowledge, especially around Bootstrapping & Squid Proxy, Https, scripting equivalent knowledge. Further align the network to meet the Companyās objectives through continuous developments, improvements and automation.
Preferably 10+ years of experience in network design and delivery of technology centric, customer-focused services.
Preferably 3+ years in modern software-defined network and preferably, in cloud-based environments.
Diploma or bachelorās degree in engineering, Computer Science/Information Technology, or its equivalent.
Preferably possess a valid RHCE (Red Hat Certified Engineer) certification
Preferably possess any vendor Proxy certification (Forcepoint/ Websense/ bluecoat / equivalent)
Must possess advanced knowledge in TCP/IP concepts and fundamentals. ļ· Good understanding and working knowledge of Squid proxy, Https protocol / Certificate management.
Fundamental understanding of proxy & PAC file.
Integration experience and knowledge between modern networks and cloud service providers such as AWS, Azure and GCP will be advantageous.
Knowledge in SaaS, IaaS, PaaS, and virtualization will be advantageous.
Coding skills such as Perl, Python, Shell scripting will be advantageous.
Excellent technical knowledge, troubleshooting, problem analysis, and outside-the-box thinking.
Excellent communication skills ā oral, written and presentation, across various types of target audiences.
Strong sense of personal ownership and responsibility in accomplishing the organizationās goals and objectives. Exudes confidence, able to cope under pressure and will roll-up his/her sleeves to drive a project to success in a challenging environment.
Key Responsibilities
2-5 years of experience is a must
Should be hands on in all aspects of IT Recruitment (Sourcing, screening, coordinating, negotiation, on-boarding etc)
Searching for and Approaching Suitable Candidates.
Running Job Ads To Attract Applicants.
Managing the Interview, Assessment, and Shortlisting Processes.
Maintaining a Database.
Preferably from corporate hiring background.
Coaching and Mentoring Junior Recruiters.
Excellent communication skills are mandatory.
Good team player.
Ā
Education:-
Bachelors or Equivalent
- Manages the company's social media accounts and posts content.
- Monitor various social media platforms such as Facebook, Instagram, and Twitter.
C++ā¢ C++ , Unix Environment ( Linux/AIX/HP UX), Oracle/MySQL
ā¢ Excellent command on OOPS
ā¢ Minimum of 3 years (for Mid and Junior) of hands-on work experience in C++, Unix
ā¢ Oracle/MySQL
ā¢ Hands-on experience of using data structures, STL, Boost libraries, Design patterns
ā¢ Exposure to XML or Edifact is desired
ā¢ Exposure to XSLT mappings is a plus
ā¢ Excellent troubleshooting skills
ā¢ Exposure to CppUnit (or similar tools)
Experience range:
ā¢ 4 to 8 years of experience
Joining Location:
ā¢ Pune, Gandhinagar & Hyderabad (Preferably Pune & Gandhinagar)
We are looking for a Functional Consultant to join our team and play a key role in the implementation and support of our software solutions for clients. This is a remote, full-time opportunity ideal for someone who enjoys working closely with customers, solving problems, and improving business processes through technology.
This role requires strong willingness to learn and understand our product in depth, as well as a proactive attitude toward continuous learning and growth within the company.
Key Responsibilities
- Act as a liaison between clients and the technical team to understand business requirements.
- Configure and deploy the software platform based on client needs.
- Learn the product thoroughly to provide effective client onboarding, training, and support.
- Conduct virtual client training and user onboarding sessions.
- Create and maintain implementation documentation and training resources.
- Provide post-implementation support and resolve client issues in a timely manner.
- Collaborate with internal teams to enhance product functionality and user experience.
- Support data migration and UAT (User Acceptance Testing) phases during onboarding.
Qualifications
- Bachelor's degree in any discipline (preferred: Engineering, IT, Business, Food Technology).
- 0ā2 years of experience in a functional, consulting, or client-facing role.
- Excellent communication and presentation skills.
- Eagerness to learn new tools, systems, and product functionalities.
- Strong problem-solving ability and attention to detail.
- Basic understanding of SaaS platforms or ERP/CRM systems is a plus.
- Self-motivated with the ability to work independently in a remote setup.
What We Offer
- Flexible remote working environment.
- A strong learning curve with hands-on client projects and product knowledge.
- Supportive and collaborative team culture.
- Long-term growth opportunities within the company.
JavaPython
Go Programming (Golang)
NodeJS (Node.js)
Spring BootArchitect, develop and maintain highly scalable, reliable and secure distributed backend
systems on Cloud (AWS or Azure) or on-premises environments for Mihup, its customers
and partners.
ļ· Work closely with your fellow engineers to develop systems capable of concurrently
processing massive amounts of voice data both in online real-time as well as offline
environments.
ļ· Drive accountability for test driven development, delivery of high-quality features and
resilient enterprise class solutions.
ļ· Lead a culture of team ownership and direct individual and team accountability to
continuously improve how they work to achieve results.
ļ· Work in a startup environment, pushing boundaries with deep involvement with business.
BE//BTech/ME/MTech in Computer Science or a related field from a Tier I or Tier II
University.
ļ· 6-8 years of hands-on software development and deployment experience (experience of
working in a consumer product startup during its growth phase will be a plus) of which 1 ā 2
years of experience would be in leading a team of software developers.
ļ· Expertise in Java 8+ and Spring Boot is a must
ļ· Good experience in messaging platforms like RabbitMQ/Kafka
ļ· Good experience in distributed systems and relational & NoSQL databases like PostgreSQL,
MySQL, Redis, MongoDB, etc.
ļ· Expertise in one or more of: Python, NodeJS, GoLang would be preferred
ļ· Must have hands on experience in products which handle multiple concurrent calls (API),
handle CPU intensive jobs, consist of multiple asynchronous system calls.
ļ· Worked on microservices based architecture and design
ļ· Managed/ Owned infrastructure on AWS/Microsoft Azure/private clouds and setup high
availability systems
ļ· Knowledge of Docker and Kubernetes
ļ· Knowledge of RESTful APIs, caching concepts, the HTTP protocol and general web
architecture
Pluses
1. Anything that will let us know more about who you are that you would like to share such as
Blogs, Twitter, Medium, GitHub etc.Ā
Skills Required
- Generate business via portals like Upwork, Guru, PPH and Freelancer.
- UpworkĀ response handlingĀ to mature business opportunities and Interact with clients
- Must have technical knowledge of Mobile and Web Development technologies, if you donāt have technical know how, please donāt apply.
- Explore and develop new business opportunities and understand clients' requirements and acquisition.
Qualifications
- In depth knowledge of online marketplaces i.e. Upwork, PPH, Guru etc.
- Bringing new projects through bidding, Client communication, Proposal writing,
- Excellent communication & interpersonal skills, Flair for business development.
- Sound knowledge of IT technologies
Follow CutshortShubham Vishwakarma
Full Stack Developer - Averlon